Update app.py

app.py

@@ -1,34 +1,25 @@
 import os
 import gradio as gr
-import numpy as np
 from transformers import AutoTokenizer, AutoModel
 from scipy.special import softmax
-
-import gradio as gr
-import numpy as np
-import pandas as pd
-import pickle
-import transformers
-from transformers import AutoTokenizer, AutoConfig,AutoModelForSequenceClassification,TFAutoModelForSequenceClassification, pipeline
-from scipy.special import softmax
-from dotenv import load_dotenv, dotenv_values
 from huggingface_hub import login
+
+# Load environment variables
+from dotenv import load_dotenv
 load_dotenv()
+
 # Get the token from the environment variable
 access_token = os.getenv("access_token")
-login(os.getenv("access_token"))
 
+# Log in to Hugging Face (commented out for now)
+# login(access_token)
 
 # Requirements
-
 model_path = "imalexianne/distilbert-base-uncased"
 tokenizer = AutoTokenizer.from_pretrained(model_path)
+model = AutoModel.from_pretrained(model_path)
 
-
-config = AutoConfig.from_pretrained(model_path)
-model = AutoModelForSequenceClassification.from_pretrained(model_path)
-
-# Preprocessessing function
+# Preprocessing function
 def preprocess(text):
     new_text = []
     for x in text.split(" "):
@@ -37,30 +28,28 @@ def preprocess(text):
         new_text.append(x)
     return " ".join(new_text)
 
-# ---- Function to process the input and return prediction
+# Function to process the input and return prediction
 def sentiment_analysis(text):
     text = preprocess(text)
-
-    encoded_input = tokenizer(text, return_tensors = "pt") # for PyTorch-based models
+    encoded_input = tokenizer(text, return_tensors="pt")
     output = model(**encoded_input)
-    scores_ = output[0][0].detach().numpy()
+    scores_ = output.logits[0].detach().numpy()
     scores_ = softmax(scores_)
     
     # Format output dict of scores
     labels = ["Negative", "Neutral", "Positive"]
-    scores = {l:float(s) for (l,s) in zip(labels, scores_) }
+    scores = {l: float(s) for (l, s) in zip(labels, scores_)}
     
     return scores
 
-
-# ---- Gradio app interface
-app = gr.Interface(fn = sentiment_analysis,
-                   inputs = gr.Textbox("Write your text here..."),
-                   outputs = "label",
-                   title = "Sentiment Analysis of Tweets on COVID-19 Vaccines",
-                   description  = "Sentiment Analysis of text based on tweets about COVID-19 Vaccines using a fine-tuned 'distilbert-base-uncased' model",
-                  
-                   examples = [["Covid vaccination has no positive impact"]]
-                   )
+# Gradio app interface
+app = gr.Interface(
+    fn=sentiment_analysis,
+    inputs=gr.Textbox("Write your text here..."),
+    outputs="label",
+    title="Sentiment Analysis of Tweets on COVID-19 Vaccines",
+    description="Sentiment Analysis of text based on tweets about COVID-19 Vaccines using a fine-tuned 'distilbert-base-uncased' model",
+    examples=[["Covid vaccination has no positive impact"]]
+)
 
 app.launch()